Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code snippets related to setting values or properties in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Value
    -0.19
     setup
    -0.19
     setups
    -0.17
    _setup
    -0.17
    agara
    -0.17
    -setup
    -0.16
    setup
    -0.16
    Setup
    -0.16
    è¨Ńå®ļ
    -0.16
    vrier
    -0.16
    POSITIVE LOGITS
    tle
    0.42
    tlement
    0.35
    ters
    0.34
    ted
    0.31
    jmp
    0.31
    elah
    0.30
    table
    0.28
    tee
    0.27
    TING
    0.27
    sockopt
    0.27
    Act Density 0.122%

    No Known Activations